| Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT | Jul 14, 2023 | QNLIQQP | —Unverified | 0 |
| A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching | Mar 5, 2024 | ChatbotCommunity Question Answering | —Unverified | 0 |
| Have Attention Heads in BERT Learned Constituency Grammar? | Feb 16, 2021 | Natural Language InferenceNatural Language Understanding | —Unverified | 0 |
| Increasing Robustness to Spurious Correlations using Forgettable Examples | Nov 16, 2020 | Out-of-Distribution GeneralizationQQP | —Unverified | 0 |
| KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding | Apr 9, 2021 | Graph EmbeddingKnowledge Graph Embedding | —Unverified | 0 |
| Margin-Based Regularization and Selective Sampling in Deep Neural Networks | Sep 13, 2020 | ClassificationGeneral Classification | —Unverified | 0 |
| Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching | Jan 20, 2020 | QQP | —Unverified | 0 |
| On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks | Oct 15, 2020 | Active LearningOpen-Domain Question Answering | —Unverified | 0 |
| From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression | Dec 14, 2021 | Contrastive LearningLanguage Modeling | CodeCode Available | 0 |
| Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level | May 13, 2021 | QQPSST-2 | CodeCode Available | 0 |
